Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 365 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3978. Min Range: -4.3978

Max Act: 4.3978. Min Act: -0.0000

Data Index: 36151 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 4.3978. Min Range: -4.3978

Max Act: 4.3041. Min Act: -0.0000

Data Index: 1120842 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 4.3978. Min Range: -4.3978

Max Act: 4.2554. Min Act: -0.0000

Data Index: 1098529 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.9959. Min Act: -0.0000

Data Index: 24774 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.8355. Min Act: -0.0000

Data Index: 765747 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.9310. Min Act: -0.0000

Data Index: 209005 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.9646. Min Act: -0.0000

Data Index: 834640 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.6958. Min Act: -0.0000

Data Index: 359448 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.8570. Min Act: -0.0000

Data Index: 875171 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.4932. Min Act: -0.0000

Data Index: 364511 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.9990. Min Act: -0.0000

Data Index: 1057125 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.5938. Min Act: -0.0000

Data Index: 203270 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.8929. Min Act: -0.0000

Data Index: 1228096 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.7086. Min Act: -0.0000

Data Index: 1218948 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.5356. Min Act: -0.0000

Data Index: 1152985 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 4.3978. Min Range: -4.3978

Max Act: 4.0637. Min Act: -0.0000

Data Index: 753501 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.3492. Min Act: -0.0000

Data Index: 1068310 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.6482. Min Act: -0.0000

Data Index: 473207 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.8171. Min Act: -0.0000

Data Index: 873562 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.4762. Min Act: -0.0000

Data Index: 533328 (C4 (Web Text))

Max Activating Token Index: 749